Fast Zero-Shot Image Tagging
Paper: | Fast Zero-Shot Image Tagging |
Contact: | Yang Zhang, Boqing Gong, and Mubarak Shah |
Zero-shot: assign to query image both seen & unseen tags (unseen at training)
Fast: O(n) training, O(1) testing; tag thousands of images in seconds
Accurate: state-of-the-art on 2 datasets, 3 tagging tasks, & various metrics
Note: Keras & Theano are required
A conventional tagging toy example on IAPR TC-12 dataset can be downloaded here. See included readme for more details.
Given an image, its relevant tag’s word vectors rank ahead of the irrelevant tag’s along some direction in the word vector space. We call that direction the principal direction for the image. To solve the problem of image tagging, we thus learn a function to approximate the principal direction from an image. This function takes as the input an image and outputs a vector for defining the principal direction in the word vector space.
Presentation
Please refer to following papers if you want to cite our work in your publication:
@InProceedings{Zhang_2016_CVPR,
author = {Zhang, Yang and Gong, Boqing and Shah, Mubarak},
title = {Fast Zero-Shot Image Tagging},
booktitle = {The IEEE Conference on Computer Vision and Pattern
Recognition (CVPR)},
month = {June},
year = {2016}
}
Infinite-Label Learning with Semantic Output Codes
@misc{1608.06608,
Author = {Yang Zhang and Rupam Acharyya and Ji Liu and
Boqing Gong},
Title = {Infinite-Label Learning with Semantic Output Codes},
Year = {2016},
Eprint = {arXiv:1608.06608},
}